Pixazo API→Models→Minimax
Pixazo API→Models→Minimax

Minimax Music 2.6 API, Minimax Speech 2.6 API, Minimax Image API: Pricing, Documentation

by MiniMax

View as Markdown

Minimax Music 2.6 API, developers can access all MiniMax modalities including text-to-video, image generation, voice synthesis, and music creation. The API provides a unified interface for multimodal content generation, ideal for applications requiring diverse media outputs.

Get API Key
MiniMax AI API

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

MiniMax Music 2.6 API Documentation

https://gateway.pixazo.ai/minimax-music-generation-2-6/v1/generate

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

Music generate request - MiniMax Music Generation 2.6 API

Request Code

POST https://gateway.pixazo.ai/minimax-music-generation-2-6/v1/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "calm lo-fi hip hop with mellow piano",
  "is_instrumental": true
}
import requests

url = "https://gateway.pixazo.ai/minimax-music-generation-2-6/v1/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "calm lo-fi hip hop with mellow piano",
    "is_instrumental": True
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/minimax-music-generation-2-6/v1/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'calm lo-fi hip hop with mellow piano',
  is_instrumental: true
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -X POST "https://gateway.pixazo.ai/minimax-music-generation-2-6/v1/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "calm lo-fi hip hop with mellow piano",
    "is_instrumental": true
  }'

Output

{
  "request_id": "minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "minimax-music-generation-2-6",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp3"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "minimax-music-generation-2-6",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - Music generate request

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring—10–2000 charactersDescription of the desired music style, mood, genre, and scenario. Drives the composition.
lyricsNostring—Up to 3500 charactersSong lyrics for vocal tracks. Use \n to separate lines, with optional structure tags such as [Intro], [Verse], [Chorus], [Bridge], [Outro]. Required for vocal output unless lyrics_optimizer is enabled; ignored when is_instrumental is true.
sample_rateNointeger4410016000, 24000, 32000, 44100Audio sample rate in Hz. Higher = higher fidelity, larger files.
bitrateNointeger25600032000, 64000, 128000, 256000Audio bitrate in bits/sec. Higher = better quality, larger files.
formatNostringmp3mp3, wav, pcmOutput audio container/codec.
lyrics_optimizerNobooleanfalsetrue, falseWhen true and lyrics is empty, the model auto-generates lyrics from the prompt. Ignored if lyrics is provided.
is_instrumentalNobooleanfalsetrue, falseWhen true, generates instrumental music (no vocals) and lyrics is ignored.

Example Request

{
  "prompt": "Upbeat synthwave with retro arcade vibes, 120 BPM, layered analog synths",
  "lyrics": "[Verse 1]\nNeon lights are calling out\nDigital dreams without a doubt\n[Chorus]\nWe are alive in the night\nDancing in electric light",
  "sample_rate": 44100,
  "bitrate": 256000,
  "format": "mp3",
  "lyrics_optimizer": false,
  "is_instrumental": false
}

Response

{
  "request_id": "minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance. Required: $0.08"
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'minimax-music-generation-2-6' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "minimax-music-generation-2-6",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "minimax-music-generation-2-6",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/minimax-music-generation-2-6_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp3"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-04-04T06:15:23.699Z",
  "updated_at": "2026-04-04T06:16:20.000Z",
  "completed_at": "2026-04-04T06:16:20.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type (audio/mpeg)
created_atstringWhen request was created
completed_atstring|nullWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

MiniMax Music 2.6 API Pricing

Your request will cost $0.15 per song generation.
2. MiniMax Speech 2.8 HD

MiniMax Speech 2.8 HD API Documentation

https://gateway.pixazo.ai/minimax-speech-2-8-hd/v1/minimax-speech-2-8-hd-request

Authentication

All requests require an API key passed via header.

Header Type Required Description
Ocp-Apim-Subscription-Key string Yes Your API subscription key

MiniMax Speech 2.8 HD generate request - MiniMax Speech 2.8 HD

Request Code

POST /minimax-speech-2-8-hd-request HTTP/1.1
Host: gateway.pixazo.ai
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "The research findings indicate a significant correlation between sleep quality and cognitive performance in adults over fifty.",
  "output_format": "hex"
}
import requests

url = "https://gateway.pixazo.ai/minimax-speech-2-8-hd/v1/minimax-speech-2-8-hd-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "The research findings indicate a significant correlation between sleep quality and cognitive performance in adults over fifty.",
    "output_format": "hex"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
fetch("https://gateway.pixazo.ai/minimax-speech-2-8-hd/v1/minimax-speech-2-8-hd-request", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    prompt: "The research findings indicate a significant correlation between sleep quality and cognitive performance in adults over fifty.",
    output_format: "hex"
  })
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error("Error:", error));
curl -X POST "https://gateway.pixazo.ai/minimax-speech-2-8-hd/v1/minimax-speech-2-8-hd-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "The research findings indicate a significant correlation between sleep quality and cognitive performance in adults over fifty.",
    "output_format": "hex"
  }'

Output

{
  "request_id": "minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "minimax-speech-2-8-hd",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.wav"
    ],
    "media_type": "audio/wav"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "minimax-speech-2-8-hd",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - MiniMax Speech 2.8 HD generate request

Field Type Required Default Description
prompt string Yes — Text to convert to speech. Must be valid UTF-8. Use <#x#> for pauses (x = 0.01-99.99 seconds). Supports interjection tags such as (laughs), (sighs), (coughs), (clears throat), (gasps), (sniffs), (groans), (yawns).
voice_setting object No — Voice configuration. Nested fields: voice_id (string, default "Wise_Woman"); speed (float, 0.5-2.0, default 1); vol (float, 0-10, default 1); pitch (integer, -12 to 12, default 0); emotion (one of happy, sad, angry, fearful, disgusted, surprised, neutral); english_normalization (boolean) - improves number reading, with a slight latency increase.
audio_setting object No — Audio output configuration. Nested fields: sample_rate (one of 8000, 16000, 22050, 24000, 32000, 44100; default 32000); bitrate (one of 32000, 64000, 128000, 256000; default 128000); format (one of mp3, pcm, flac; default mp3); channel (1 = mono, 2 = stereo; default 1).
language_boost string No — Enhance recognition of a specific language or dialect. One of: Chinese, Chinese,Yue, English, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Slovak, Swedish, Croatian, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Afrikaans, auto.
output_format string No hex Format of the returned audio content (non-streaming only). Allowed: "hex" (hex-encoded audio, default) or "url" (hosted file URL).
pronunciation_dict object No — Custom pronunciation dictionary. Nested field: tone_list (array of strings) - replacements in the format ['text/(pronunciation)', ...].
normalization_setting object No — Loudness normalization settings. Nested fields: enabled (boolean, default true); target_loudness (float, default -18 LUFS); target_range (float, default 8 LU); target_peak (float, default -0.5 dBTP).
voice_modify object No — Voice modification. Nested fields: pitch (integer, -100 to 100); intensity (integer, -100 to 100); timbre (integer, -100 to 100).

Minimum Request

{
  "prompt": "The research findings indicate a significant correlation between sleep quality and cognitive performance in adults over fifty.",
  "output_format": "hex"
}

Full Request (all options)

{
  "prompt": "The research findings indicate a significant correlation between sleep quality and cognitive performance in adults over fifty.",
  "output_format": "hex"
}

Response

{
  "request_id": "minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Type application/json
Cache-Control no-cache
Ocp-Apim-Subscription-Key Your API subscription key

Response Handling

Common status codes for MiniMax Speech 2.8 HD generate request.

Code Meaning
202 Accepted — Request queued
Bad Request
401 Unauthorized
403 Forbidden
404 Not Found
Too Many Requests
500 Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'minimax-speech-2-8-hd' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "minimax-speech-2-8-hd",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET /v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "/v2/requests/status/minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "minimax-speech-2-8-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "minimax-speech-2-8-hd",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/minimax-speech-2-8-hd_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstring|nullWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

MiniMax Speech 2.8 HD API Pricing

Your request will cost $0.05 per 1,000 characters.
3. MiniMax Voice Design v1

MiniMax Voice Design v1 API Documentation

https://gateway.pixazo.ai/minimax-voice-design-api-363/v1/minimax-voice-design-api-request

Authentication

All requests require an API key passed via header.

Header Type Required Description
Ocp-Apim-Subscription-Key string Yes Your API subscription key

MiniMax Voice Design API generate request - MiniMax Voice Design

Request Code

POST /minimax-voice-design-api-request HTTP/1.1
Host: gateway.pixazo.ai
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic", 
"preview_text": "Oh my gosh, hi. It iss like so amazing to be here. This new endpoint just dropped on pixazo and the results have been like totally incredible. Use it now, It is gonna be like epic!"
}
import requests

url = "https://gateway.pixazo.ai/minimax-voice-design-api-363/v1/minimax-voice-design-api-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic",
    "preview_text": "Oh my gosh, hi. It iss like so amazing to be here. This new endpoint just dropped on pixazo and the results have been like totally incredible. Use it now, It is gonna be like epic!"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/minimax-voice-design-api-363/v1/minimax-voice-design-api-request';

const data = {
  prompt: "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic",
  preview_text: "Oh my gosh, hi. It iss like so amazing to be here. This new endpoint just dropped on pixazo and the results have been like totally incredible. Use it now, It is gonna be like epic!"
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -X POST "https://gateway.pixazo.ai/minimax-voice-design-api-363/v1/minimax-voice-design-api-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic",
    "preview_text": "OOh my gosh, hi. It iss like so amazing to be here. This new endpoint just dropped on pixazo and the results have been like totally incredible. Use it now, It is gonna be like epic!"
  }'

Output

{
  "request_id": "minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "minimax-voice-design-api-363",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.wav"
    ],
    "media_type": "audio/wav"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "minimax-voice-design-api-363",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - MiniMax Voice Design API generate request

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring—Up to 2000 charactersA natural language description of the desired voice personality, tone, and characteristics (e.g., age, gender, emotion, style). This defines the unique vocal identity to be synthesized.
preview_textYesstring—Up to 500 charactersThe sample text that will be spoken by the generated voice. Must be a natural, expressive phrase that demonstrates the intended vocal style.

Minimum Request

{
  "prompt": "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic",
  "preview_text": "Oh my gosh, hi. It's like so amazing to be here."
}

Full Request (all options)

{
  "prompt": "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic",
  "preview_text": "Oh my gosh, hi. It iss like so amazing to be here. This new endpoint just dropped on pixazo and the results have been like totally incredible. Use it now, It is gonna be like epic!"
}

Response

{
  "request_id": "minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Type application/json
Cache-Control no-cache
Ocp-Apim-Subscription-Key Your API subscription key

Response Handling

Common status codes for MiniMax Voice Design API generate request.

Code Meaning
202 Accepted — Request queued
Bad Request
401 Unauthorized
403 Forbidden
404 Not Found
Too Many Requests
500 Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'minimax-voice-design-api-363' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "minimax-voice-design-api-363",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET /v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "/v2/requests/status/minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "minimax-voice-design-api-363_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "minimax-voice-design-api-363",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/minimax-voice-design-api-363_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstring|nullWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

MiniMax Voice Design v1 API Pricing

Your request will cost $0.03 per 1,000 characters.
4. MiniMax Image 01

MiniMax Image 01 API Documentation

https://gateway.pixazo.ai/image-generation/v1/i2i

Image to Image - Minimax Image Generation API

Request Code

POST https://gateway.pixazo.ai/image-generation/v1/i2i
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A girl looking into the distance from a library window",
  "subject_reference": [
    {
      "type": "character",
      "image_file": "https://example.com/input-image.jpg"
    }
  ]
}
import requests

url = "https://gateway.pixazo.ai/image-generation/v1/i2i"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A girl looking into the distance from a library window",
    "subject_reference": [
        {
            "type": "character",
            "image_file": "https://example.com/input-image.jpg"
        }
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/image-generation/v1/i2i';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};

const data = {
  prompt: 'A girl looking into the distance from a library window',
  subject_reference: [
    {
      type: 'character',
      image_file: 'https://example.com/input-image.jpg'
    }
  ]
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -v -X POST "https://gateway.pixazo.ai/image-generation/v1/i2i" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A girl looking into the distance from a library window",
    "subject_reference": [
      {
        "type": "character",
        "image_file": "https://example.com/input-image.jpg"
      }
    ]
  }'

Output

{
  "id": "03ff3cd0820949eb8a410056b5f21d38",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/..."
  ],
  "image_count": 4
}
Try Now

Request Parameters - Image to Image

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text description of desired modifications or style to apply to the input image.
subject_referenceYesarray——Array of reference images. Each object contains: `type` ("character", "object", etc.) and `image_file` (URL or base64). Images must be <10MB, JPG/JPEG/PNG format.
modelNostringimage-01image-01Model name. Currently only "image-01" is supported.
aspect_ratioNostring1:1"1:1" (1024x1024), "16:9" (1280x720), "4:3" (1152x864), "3:2" (1248x832), "2:3" (832x1248), "3:4" (864x1152), "9:16" (720x1280), "21:9" (1344x576)Image aspect ratio. Options: "1:1" (1024x1024), "16:9" (1280x720), "4:3" (1152x864), "3:2" (1248x832), "2:3" (832x1248), "3:4" (864x1152), "9:16" (720x1280), "21:9" (1344x576).
widthNointeger—512–2048 (divisible by 8)Image width in pixels (512-2048, divisible by 8). Must be used with height. aspect_ratio takes priority if both are provided.
heightNointeger—512–2048 (divisible by 8)Image height in pixels (512-2048, divisible by 8). Must be used with width. aspect_ratio takes priority if both are provided.
response_formatNostringurl"url" (expires in 24 hours) or "base64"Response format. Options: "url" (expires in 24 hours) or "base64".
seedNointeger——Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
nNointeger11–9Number of images to generate (1-9).
prompt_optimizerNobooleanfalsetrue, falseAutomatically rewrites and enriches your prompt with extra detail before generation to improve results.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image1JPG, PNG · < 10 MBSubject / style reference image.

Example Request

{
  "prompt": "A futuristic cyberpunk cityscape at night, neon lights, flying cars, dramatic shadows, highly detailed, cinematic lighting",
  "subject_reference": [
    {
      "type": "character",
      "image_file": "https://example.com/input-image.jpg"
    },
    {
      "type": "object",
      "image_file": "https://example.com/reference-object.png"
    }
  ],
  "model": "image-01",
  "aspect_ratio": "16:9",
  "response_format": "url",
  "seed": 98765,
  "n": 4,
  "prompt_optimizer": true
}

Response

{
  "id": "03ff3cd0820949eb8a410056b5f21d38",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/i2i-1234567890-123456-1.png",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/i2i-1234567890-123456-2.png",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/i2i-1234567890-123456-3.png",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/i2i-1234567890-123456-4.png"
  ],
  "image_count": 4,
  "metadata": {
    "success_count": "4",
    "failed_count": "0"
  },
  "base_resp": {
    "status_code": 0,
    "status_msg": "success"
  }
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes for Image to Image.

Code Meaning
200 Success
Bad Request
401 Unauthorized
403 Forbidden
404 Not Found
Too Many Requests
500 Internal Server Error

MiniMax Image 01 API Pricing

Your request will cost $0.02 per image.
Text to Image

MiniMax Image 01 API Documentation

https://gateway.pixazo.ai/image-generation/v1/t2i

Text to Image - Minimax Image Generation API

Request Code

POST https://gateway.pixazo.ai/image-generation/v1/t2i
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A beautiful sunset over mountains"
}
import requests

url = "https://gateway.pixazo.ai/image-generation/v1/t2i"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A beautiful sunset over mountains"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/image-generation/v1/t2i';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'A beautiful sunset over mountains'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -v -X POST "https://gateway.pixazo.ai/image-generation/v1/t2i" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A beautiful sunset over mountains"
  }'

Output

{
  "id": "03ff3cd0820949eb8a410056b5f21d38",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/t2i-1234567890-123456-1.png"
  ],
  "image_count": 1
}
Try Now

Request Parameters - Text to Image

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text description of the image, maximum 1500 characters.
modelNostringimage-01image-01Model name. Currently only "image-01" is supported.
aspect_ratioNostring1:1"1:1" (1024x1024), "16:9" (1280x720), "4:3" (1152x864), "3:2" (1248x832), "2:3" (832x1248), "3:4" (864x1152), "9:16" (720x1280), "21:9" (1344x576)Image aspect ratio. Options: "1:1" (1024x1024), "16:9" (1280x720), "4:3" (1152x864), "3:2" (1248x832), "2:3" (832x1248), "3:4" (864x1152), "9:16" (720x1280), "21:9" (1344x576).
widthNointeger—512–2048 (divisible by 8)Image width in pixels (512-2048, divisible by 8). Must be used with height. aspect_ratio takes priority if both are provided.
heightNointeger—512–2048 (divisible by 8)Image height in pixels (512-2048, divisible by 8). Must be used with width. aspect_ratio takes priority if both are provided.
response_formatNostringurl"url" (expires in 24 hours) or "base64"Response format. Options: "url" (expires in 24 hours) or "base64".
seedNointeger——Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
nNointeger11–9Number of images to generate (1-9).
prompt_optimizerNobooleanfalsetrue, falseAutomatically rewrites and enriches your prompt with extra detail before generation to improve results.

Example Request

{
  "prompt": "A man in a white t-shirt, full-body, standing front view, outdoors, with the Venice Beach sign in the background, Los Angeles. Fashion photography in 90s documentary style, film grain, photorealistic.",
  "model": "image-01",
  "aspect_ratio": "16:9",
  "response_format": "url",
  "seed": 12345,
  "n": 3,
  "prompt_optimizer": true
}

Response

{
  "id": "03ff3cd0820949eb8a410056b5f21d38",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/t2i-1234567890-123456-1.png",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/t2i-1234567890-123456-2.png",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/minimax_images/t2i-1234567890-123456-3.png"
  ],
  "image_count": 3,
  "metadata": {
    "success_count": "3",
    "failed_count": "0"
  },
  "base_resp": {
    "status_code": 0,
    "status_msg": "success"
  }
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes for Text to Image.

Code Meaning
200 Success
Bad Request
401 Unauthorized
403 Forbidden
404 Not Found
Too Many Requests
500 Internal Server Error

MiniMax Image 01 API Pricing

Your request will cost $0.02 per image.